The DiCOVA challenge aims at accelerating research in diagnosing COVID-19 using acoustics (DiCOVA), a topic at the intersection of speech and audio processing, respiratory health diagnosis, and machine learning. This challenge is an open call for researchers to analyze a dataset of sound recordings collected from COVID-19 infected and non-COVID-19 individuals for a two-class classification. These recordings were collected via crowdsourcing from multiple countries, through a website application. The challenge features two tracks, one focuses on using cough sounds, and the other on using a collection of breath, sustained vowel phonation, and number counting speech recordings. In this paper, we introduce the challenge and provide a detailed description of the dataset, task, and present a baseline system for the task.
The recently proposed Sequence-to-Sequence (seq2seq) framework advocates replacing complex data processing pipelines, such as an entire automatic speech recognition system, with a single neural network trained in an end-to-end fashion. In this contribution, we analyse an attention-based seq2seq speech recognition system that directly transcribes recordings into characters. We observe two shortcomings: overconfidence in its predictions and a tendency to produce incomplete transcriptions when language models are used. We propose practical solutions to both problems achieving competitive speaker independent word error rates on the Wall Street Journal dataset: without separate language models we reach 10.6% WER, while together with a trigram language model, we reach 6.7% WER.
Bidirectional Long Short-Term Memory Recurrent Neural Network (BLSTM-RNN) has been shown to be very effective for modeling and predicting sequential data, e.g. speech utterances or handwritten documents. In this study, we propose to use BLSTM-RNN for a unified tagging solution that can be applied to various tagging tasks including part-of-speech tagging, chunking and named entity recognition. Instead of exploiting specific features carefully optimized for each task, our solution only uses one set of task-independent features and internal representations learnt from unlabeled text for all tasks.Requiring no task specific knowledge or sophisticated feature engineering, our approach gets nearly state-of-the-art performance in all these three tagging tasks.
This work explores constituency parsing on automatically recognized transcripts of conversational speech. The neural parser is based on a sentence encoder that leverages word vectors contextualized with prosodic features, jointly learning prosodic feature extraction with parsing. We assess the utility of the prosody in parsing on imperfect transcripts, i.e. transcripts with automatic speech recognition (ASR) errors, by applying the parser in an N-best reranking framework. In experiments on Switchboard, we obtain 13-15% of the oracle N-best gain relative to parsing the 1-best ASR output, with insignificant impact on word recognition error rate. Prosody provides a significant part of the gain, and analyses suggest that it leads to more grammatical utterances via recovering function words.
The prosody of a spoken word is determined by its surrounding context. In incremental text-to-speech synthesis, where the synthesizer produces an output before it has access to the complete input, the full context is often unknown which can result in a loss of naturalness in the synthesized speech. In this paper, we investigate whether the use of predicted future text can attenuate this loss. We compare several test conditions of next future word: (a) unknown (zero-word), (b) language model predicted, (c) randomly predicted and (d) ground-truth. We measure the prosodic features (pitch, energy and duration) and find that predicted text provides significant improvements over a zero-word lookahead, but only slight gains over random-word lookahead. We confirm these results with a perceptive test.
This paper introduces FastVC, an end-to-end model for fast Voice Conversion (VC). The proposed model can convert speech of arbitrary length from multiple source speakers to multiple target speakers. FastVC is based on a conditional AutoEncoder (AE) trained on non-parallel data and requires no annotations at all. This model's latent representation is shown to be speaker-independent and similar to phonemes, which is a desirable feature for VC systems. While the current VC systems primarily focus on achieving the highest overall speech quality, this paper tries to balance the development concerning resources needed to run the systems. Despite the simple structure of the proposed model, it outperforms the VC Challenge 2020 baselines on the cross-lingual task in terms of naturalness.
The goal of this work is to train strong models for visual speech recognition without requiring human annotated ground truth data. We achieve this by distilling from an Automatic Speech Recognition (ASR) model that has been trained on a large-scale audio-only corpus. We use a cross-modal distillation method that combines CTC with a frame-wise cross-entropy loss. Our contributions are fourfold: (i) we show that ground truth transcriptions are not necessary to train a lip reading system; (ii) we show how arbitrary amounts of unlabelled video data can be leveraged to improve performance; (iii) we demonstrate that distillation significantly speeds up training; and, (iv) we obtain state-of-the-art results on the challenging LRS2 and LRS3 datasets for training only on publicly available data.
Recent approaches in text-to-speech (TTS) synthesis employ neural network strategies to vocode perceptually-informed spectrogram representations directly into listenable waveforms. Such vocoding procedures create a computational bottleneck in modern TTS pipelines. We propose an alternative approach which utilizes generative adversarial networks (GANs) to learn mappings from perceptually-informed spectrograms to simple magnitude spectrograms which can be heuristically vocoded. Through a user study, we show that our approach significantly outperforms na\"ive vocoding strategies while being hundreds of times faster than neural network vocoders used in state-of-the-art TTS systems. We also show that our method can be used to achieve state-of-the-art results in unsupervised synthesis of individual words of speech.
In this paper, we present a multi-modal online person verification system using both speech and visual signals. Inspired by neuroscientific findings on the association of voice and face, we propose an attention-based end-to-end neural network that learns multi-sensory associations for the task of person verification. The attention mechanism in our proposed network learns to conditionally select a salient modality between speech and facial representations that provides a balance between complementary inputs. By virtue of this capability, the network is robust to missing or corrupted data from either modality. In the VoxCeleb2 dataset, we show that our method performs favorably against competing multi-modal methods. Even for extreme cases of large corruption or an entirely missing modality, our method demonstrates robustness over other unimodal methods.
Similes play an important role in literary texts not only as rhetorical devices and as figures of speech but also because of their evocative power, their aptness for description and the relative ease with which they can be combined with other figures of speech (Israel et al. 2004). Detecting all types of simile constructions in a particular text therefore seems crucial when analysing the style of an author. Few research studies however have been dedicated to the study of less prominent simile markers in fictional prose and their relevance for stylistic studies. The present paper studies the frequency of adjective and verb simile markers in a corpus of British and French novels in order to determine which ones are really informative and worth including in a stylistic analysis. Furthermore, are those adjectives and verb simile markers used differently in both languages?